Qwen3 Rerank API

About Qwen3 Rerank

Semantic document reranker. Sorts up to 500 candidates per query by relevance, supports 100+ languages, and accepts a custom sorting instruction.

Also known as Alibaba Cloud Qwen3 Rerank

Qwen3 Rerank specs

Model ID

qwen3-rerank

Author

Alibaba Cloud

Category

Rerankers

Released

Jun 5, 2025

Context window

4K tokens

Input

Text

Output

Ranking

Region

Singapore

Endpoints

POST/v1/reranks

Qwen3 Rerank API pricing

Live pay-as-you-go rates from the EmpirioLabs catalog. You are billed only for what you use, with no monthly minimum.

How to call the Qwen3 Rerank API

Qwen3 Rerank ranks candidate documents against a query through POST /v1/reranks with the model id qwen3-rerank. Get an API key from the EmpirioLabs dashboard.

curl https://api.empiriolabs.ai/v1/reranks \
  -H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3-rerank",
    "query": "How do I rotate an API key?",
    "documents": ["Rotate keys from the dashboard.", "Billing is pay as you go."]
  }'

import requests

response = requests.post(
    "https://api.empiriolabs.ai/v1/reranks",
    headers={"Authorization": "Bearer YOUR_EMPIRIOLABS_API_KEY"},
    json={
        "model": "qwen3-rerank",
        "query": "How do I rotate an API key?",
        "documents": ["Rotate keys from the dashboard.", "Billing is pay as you go."],
    },
)
print(response.json())

Qwen3 Rerank API parameters

Request parameters supported by the Qwen3 Rerank API on EmpirioLabs. Defaults apply when a field is omitted.

Good to know

Per-request limits

• Up to 500 candidate documents per request
• Max 4,000 tokens per query/document
• Max 120,000 tokens per request (formula: query_tokens × n_docs + sum_of_doc_tokens)
• Tokens billed are query+documents combined; only successful reranks are charged

Languages

• 100+ major languages including Chinese, English, Spanish, French, Portuguese, Indonesian, Japanese, Korean, German, Russian

Sorting modes (instruct parameter)

• *Default, Q&A retrieval*: `Given a web search query, retrieve relevant passages that answer the query.`
• *Semantic similarity*: `Retrieve semantically similar text.`
• Or any custom English instruction (see model task prompts)

Qwen3 Rerank API: common questions

How much does the Qwen3 Rerank API cost?

On EmpirioLabs, Qwen3 Rerank is billed pay as you go: Input $0.10 per 1M prompt tokens. The live rate card on this page always matches what the API charges.

What is the context window of Qwen3 Rerank?

Qwen3 Rerank supports a 4K-token context window.

Which endpoint does Qwen3 Rerank use?

Qwen3 Rerank is served through POST /v1/reranks on api.empiriolabs.ai with standard bearer-token authentication.

Can I try Qwen3 Rerank in the browser before integrating?

Yes. The EmpirioLabs playground runs Qwen3 Rerank in the browser with the same parameters the API exposes, so you can test prompts before writing code.

How do I get a Qwen3 Rerank API key?

Create an EmpirioLabs account, then generate a key under API Keys in the dashboard. Billing is pay-as-you-go credits, so you only pay for the requests you make.